Hacker News new | past | comments | ask | show | jobs | submit login
Official Google Blog: A picture of a thousand words? (googleblog.blogspot.com)
14 points by qhoxie on Oct 30, 2008 | hide | past | favorite | 4 comments



Who did Google acquire for the image recognition software (Optical Character Recognition) behind this?


http://en.wikipedia.org/wiki/Tesseract_OCR

It's open-source abandonware from HP.


All companies who did the same are dead now. Eventually, Google can search most image content, face and of cause scanned texts. That means, now all the companies who are founded with image recognition techs, face recognition techs can not efficiently distinguish themselves from Google. Overall, content-based retrieval is only a branch of search technology.


Well you can always have a better technology. At some point you'll need to be able to scale up but you'd definitely be an acquisition target for someone with large processing capability.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: